A two-gene random forest model to diagnose osteoarthritis based on RNA-binding protein-related genes in knee cartilage tissue.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36641761", "kind": "science-record", "revision": 3, "content_hash": "sha256:8e83f1fa7e1e702d0009afad4998399486c0e5b2732c4fdc80f8a62064625c81", "created_at": "2026-11-01T19:01:11Z", "updated_at": "2026-11-01T22:08:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A two-gene random forest model to diagnose osteoarthritis based on RNA-binding protein-related genes in knee cartilage tissue.", "doi": "10.18632/aging.204469", "pmid": "36641761", "authors": ["Wenhua Yin", "Ying Lei", "Xuan Yang", "Jiawei Zou"], "journal": "Aging", "year": 2023, "abstract": "Osteoarthritis (OA) is one of the most common diseases in the orthopedic clinic, characterized by progressive cartilage degradation. RNA-binding proteins (RBPs) are capable of binding to RNAs at transcription and translation levels, playing an important role in the pathogenesis of OA. This study aims to investigate the diagnosis values of RBP-related genes in OA. The RBPs were collected from previous studies, and the GSE114007 dataset (control = 18, OA = 20) was downloaded from the Gene Expression Omnibus (GEO) as the training cohort. Through various bioinformatical and machine learning methods, including genomic difference detection, protein-protein interaction network analyses, Lasso regression, univariate logistic regression, Boruta algorithm, and SVM-RFE, RNMT and RBM24 were identified and then included into the random forest (RF) diagnosis model. GSE117999 dataset (control = 10, OA = 10) and clinical samples collected from local hospital (control = 10, OA = 11) were used for external validation. The RF model was a promising tool to diagnose OA in the training dataset (area under curve [AUC] = 1.000, 95% confidence interval [CI] = 1.000-1.000), the GSE117999 cohort (AUC = 0.900, 95% CI = 0.769-1.000), and local samples (AUC = 0.759, 95% CI = 0.568-0.951). Besides, qPCR and Western Blotting experiments showed that RNMT (P < 0.05) and RBM24 (P < 0.01) were both down-regulated in CHON-001 cells with IL-1β treatment. In all, an RF model to diagnose OA based on RNMT and RBM24 in cartilage tissue was constructed, providing a promising clinical tool and possible cut-in points in molecular mechanism clarification.", "claims": [{"id": "claim-method", "statement": "The randomForest package in R software was used to develop the RF diagnosis model with ntree = 500 and mtry = 3.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36641761", "locator": "sections[9] \"RF model construction\" paragraph 2", "quote": "The randomForest package in R software was used to develop the RF diagnosis model with ntree = 500 and mtry = 3."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36641761", "locator": "sections[3] \"Data collection and processing\" paragraph 2", "quote": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A random forest model based on RNMT and RBM24 expression in cartilage tissue showed promising diagnostic performance for osteoarthritis in the training cohort, the GSE117999 cohort, and local clinical samples.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "The RF model was a promising tool to diagnose OA in the training dataset (area under curve [AUC] = 1.000, 95% confidence interval [CI] = 1.000-1.000), the GSE117999 cohort (AUC = 0.900, 95% CI = 0.769–1.000), and local samples (AUC = 0.759, 95% CI = 0.568–0.951)."}, "evidence": [{"asset": "source:pmid:36641761", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The RF model was a promising tool to diagnose OA in the training dataset (area under curve [AUC] = 1.000, 95% confidence interval [CI] = 1.000-1.000), the GSE117999 cohort (AUC = 0.900, 95% CI = 0.769–1.000), and local samples (AUC = 0.759, 95% CI = 0.568–0.951)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A random forest model based on RNMT and RBM24 expression in cartilage tissue showed promising diagnostic performance for osteoarthritis in the training cohort, the GSE117999 cohort, and local clinical samples.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:36641761"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE114007"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE114007"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36641761", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.204469", "sha256": "sha256:24361887013f5125194f97640caf0814f48f11abebdc4e7e9ec73c0c9c983625", "bytes": 27104, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.204469", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9876643", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE114007", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE114007", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE114007", "version": null, "note": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3130531", "GSM3130532", "GSM3130533", "GSM3130534", "GSM3130535", "GSM3130536", "GSM3130537", "GSM3130538", "GSM3130539", "GSM3130540", "GSM3130541", "GSM3130542", "GSM3130543", "GSM3130544", "GSM3130545", "GSM3130546", "GSM3130547", "GSM3130548", "GSM3130549", "GSM3130550", "GSM3130551", "GSM3130552", "GSM3130553", "GSM3130554", "GSM3130555", "GSM3130556", "GSM3130557", "GSM3130558", "GSM3130559", "GSM3130560", "GSM3130561", "GSM3130562", "GSM3130563", "GSM3130564", "GSM3130565", "GSM3130566", "GSM3130567", "GSM3130568"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "11154;18573", "taxon": "Homo sapiens", "title": "Identification of transcription factors responsible for dysregulated networks in human osteoarthritis cartilage by global gene expression analysis", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE117999", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE117999", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE117999", "version": null, "note": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3316962", "GSM3316963", "GSM3316964", "GSM3316965", "GSM3316966", "GSM3316967", "GSM3316968", "GSM3316969", "GSM3316970", "GSM3316971", "GSM3316972", "GSM3316973", "GSM3316974", "GSM3316975", "GSM3316976", "GSM3316977", "GSM3316978", "GSM3316979", "GSM3316980", "GSM3316981", "GSM3316982", "GSM3316983", "GSM3316984", "GSM3316985"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "20844", "taxon": "Homo sapiens", "title": "Transcriptome comparison of cartilage from patients with and without osteoarthritis", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE114007 not downloaded", "asset:data:geo:GSE114007 licence not read", "asset:data:geo:GSE117999 not downloaded", "asset:data:geo:GSE117999 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The randomForest package in R software was used to develop the RF diagnosis model with ntree = 500 and mtry = 3."}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-3", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": ["method.machine_learning_random_forest"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE114007", "GSE117999"], "resolved_accessions": ["GSE114007", "GSE117999"], "statements": ["GSE114007 [13], which contained the RNA sequencing (RNA-seq) data of the knee cartilage tissue isolated from 18 healthy control and 20 OA subjects, was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo/) as the training dataset."], "basis": "The paper names GSE114007, GSE117999 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36641761", "data:geo:GSE114007"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE114007"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:23:04Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 8285, "completion_tokens": 1275, "cached_tokens": 128}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:36641761", "type": "paper", "label": "pmid:36641761"}, {"id": "source:pmid:36641761", "type": "manuscript", "label": "PMID 36641761 full text"}, {"id": "data:geo:GSE114007", "type": "dataset", "label": "GEO GSE114007"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36641761", "type": "paper", "label": "pmid:36641761"}, {"id": "source:pmid:36641761", "type": "manuscript", "label": "PMID 36641761 full text"}, {"id": "data:geo:GSE114007", "type": "dataset", "label": "GEO GSE114007"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36641761", "type": "extraction", "used": ["source:pmid:36641761"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE114007", "type": "accession_resolution", "used": ["data:geo:GSE114007"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:36641761", "parent_hash": "sha256:69b4eb2917dfd7b60e2f6a04dbfc95e1816cc24857caed300844e165ed57506b", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE114007 licence not read", "asset:data:geo:GSE114007 not downloaded", "asset:data:geo:GSE117999 licence not read", "asset:data:geo:GSE117999 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["AUC = 0.759, 95% CI = 0.568-0.951). Besides, qPCR and Western Blotting experiments showed that"], "order_basis": "paper_text_order:1371", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["59, 95% CI = 0.568-0.951). Besides, qPCR and Western Blotting experiments showed that RNMT (P < 0.05) and"], "order_basis": "paper_text_order:1380", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["e Culture Collection (Manassas, VA, USA) and cultured in DMEM (Gibco; Thermo Fisher Scientific, USA)"], "order_basis": "paper_text_order:1867", "id": "assay:3"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The randomForest package in R software was used to develop the RF diagnosis model with ntree = 500 and mtry = 3."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}